Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:752b7289613ae132531ffb75e6dfec8e28513efaedd6df08b3ffcc1d370a7373
+oid sha256:d0dcf89e4bc8e9a03ec2412af43ca7340ad82c033dc543649c99d62039f35ba6
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776ea9fb330b2c1746dbbe31c7aee988d755636ff7849c89f37a892bde3cb53f
+oid sha256:87016bec416f33d16bec87880b86c9fea190ab9b48de9e1d5ce5dad52000bcc0
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7bad38b6510dcfd435e5e047c00ab3bb954cd2dc192cb4716bc78ccd281cb39
+oid sha256:4f428c8a6a024f6338900342bc9c5ff40c342f28b297a96dfc6c96a2bb31282f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007393487569699024,
+  "epoch": 0.0011090231354548535,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 30.41,
       "eval_steps_per_second": 15.209,
       "step": 6
+    },
+    {
+      "epoch": 0.0008625735497982194,
+      "grad_norm": 1.4673856496810913,
+      "learning_rate": 0.00014,
+      "loss": 7.2599,
+      "step": 7
+    },
+    {
+      "epoch": 0.0009857983426265365,
+      "grad_norm": 1.9101917743682861,
+      "learning_rate": 0.00016,
+      "loss": 6.6899,
+      "step": 8
+    },
+    {
+      "epoch": 0.0011090231354548535,
+      "grad_norm": 1.9195061922073364,
+      "learning_rate": 0.00018,
+      "loss": 7.012,
+      "step": 9
+    },
+    {
+      "epoch": 0.0011090231354548535,
+      "eval_loss": 1.7387100458145142,
+      "eval_runtime": 112.4469,
+      "eval_samples_per_second": 30.388,
+      "eval_steps_per_second": 15.198,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 358286842920960.0,
+  "total_flos": 537430264381440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null